留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

Comparison of Artificial Neural Networks, Geographically Weighted Regression and Cokriging Methods for Predicting the Spatial Distribution of Soil Macronutrients (N, P, and K)

Samad EMAMGHOLIZADEH Shahin SHAHSAVANI Mohamad Amin ESLAMI

Samad EMAMGHOLIZADEH, Shahin SHAHSAVANI, Mohamad Amin ESLAMI. Comparison of Artificial Neural Networks, Geographically Weighted Regression and Cokriging Methods for Predicting the Spatial Distribution of Soil Macronutrients (N, P, and K)[J]. 中国地理科学, 2017, 27(5): 747-759. doi: 10.1007/s11769-017-0906-6
引用本文: Samad EMAMGHOLIZADEH, Shahin SHAHSAVANI, Mohamad Amin ESLAMI. Comparison of Artificial Neural Networks, Geographically Weighted Regression and Cokriging Methods for Predicting the Spatial Distribution of Soil Macronutrients (N, P, and K)[J]. 中国地理科学, 2017, 27(5): 747-759. doi: 10.1007/s11769-017-0906-6
Samad EMAMGHOLIZADEH, Shahin SHAHSAVANI, Mohamad Amin ESLAMI. Comparison of Artificial Neural Networks, Geographically Weighted Regression and Cokriging Methods for Predicting the Spatial Distribution of Soil Macronutrients (N, P, and K)[J]. Chinese Geographical Science, 2017, 27(5): 747-759. doi: 10.1007/s11769-017-0906-6
Citation: Samad EMAMGHOLIZADEH, Shahin SHAHSAVANI, Mohamad Amin ESLAMI. Comparison of Artificial Neural Networks, Geographically Weighted Regression and Cokriging Methods for Predicting the Spatial Distribution of Soil Macronutrients (N, P, and K)[J]. Chinese Geographical Science, 2017, 27(5): 747-759. doi: 10.1007/s11769-017-0906-6

Comparison of Artificial Neural Networks, Geographically Weighted Regression and Cokriging Methods for Predicting the Spatial Distribution of Soil Macronutrients (N, P, and K)

doi: 10.1007/s11769-017-0906-6
基金项目: Under the auspices of Shahrood University of Technology,Iran (No.348517)
详细信息
    通讯作者:

    Samad EMAMGHOLIZADEH,E-mail:s_gholizadeh517@shahroodut.ac.ir

Comparison of Artificial Neural Networks, Geographically Weighted Regression and Cokriging Methods for Predicting the Spatial Distribution of Soil Macronutrients (N, P, and K)

Funds: Under the auspices of Shahrood University of Technology,Iran (No.348517)
More Information
    Corresponding author: Samad EMAMGHOLIZADEH,E-mail:s_gholizadeh517@shahroodut.ac.ir
  • 摘要: Soil macronutrients (i.e. nitrogen (N), phosphorus (P), and potassium (K)) are important soils components and knowing the spatial distribution of these parameters are necessary at precision agriculture. The purpose of this study was to evaluate the feasibility of different methods such as artificial neural networks (ANN) and two geostatistical methods (geographically weighted regression (GWR) and cokriging (CK)) to estimate N, P and K contents. For this purpose, soil samples were taken from topsoil (0-30 cm) at 106 points and analyzed for their chemical and physical parameters. These data were divided into calibration (n=84) and validation (n=22). Chemical and physical variables including clay, pH and organic carbon (OC) were used as auxiliary soil variables to estimate the N, P and K contents. Results showed that the ANN model (with coefficient of determination R2=0.922 and root mean square error RMSE=0.0079%) was more accurate compared to the CK model (with R2=0.612 and RMSE=0.0094%), and the GWR model (with R2=0.872 and RMSE=0.0089%) to estimate the N variable. The ANN model estimated the P with the RMSE of 3.630 ppm, which was respectively 28.93% and 20.00% less than the RMSE of 4.680 ppm and 4.357 ppm from the CK and GWR models. The estimated K by CK, GWR and ANN models have the RMSE of 76.794 ppm, 75.790 ppm and 52.484 ppm. Results indicated that the performance of the CK model for estimation of macro nutrients (N, P and K) was slightly lower than the GWR model. Also, the accuracy of the ANN model was higher than CK and GWR models, which proved to be more effective and reliable methods for estimating macro nutrients.
  • [1] Aggelopoulou K, Gemtos T, 2011. Delineation of management zones in an apple orchard: correlations between yield and soil properties. In: Proceedings of the International Conference on Informationand Communication Technologiesfor Sustainable Agri-production and Environment. Skiathos: HAICTA, 443– 450.
    [2] Azmathullah H M, Deo M, Deolalikar P B, 2005. Neural networks for estimation of scour downstream of a ski-jump bucket. Journal of Hydraulic Engineering, 131(10): 898–908. doi:  10.1061/(ASCE)0733-9429(2005)131:10(898)
    [3] Bateni S M, Borghei S M, Jeng D S, 2007. Neural network and neuro-fuzzy assessments for scour depth around bridge piers. Engineering Applications of Artificial Intelligence, 20(3):401–414. doi:  10.1016/j.engappai.2006.06.012
    [4] Box G E P, Cox D R, 1964. An analysis of transformations. Journal of the Royal Statistical Society. Series B (Methodological), 26(2): 211–252.
    [5] Cambardella C A, Moorman T B, Parkin T B et al., 1994. Field-scale variability of soil properties in central iowa soils. Soil Science Society of America Journal, 58(5): 1501–1511. doi:  10.2136/sssaj1994.03615995005800050033x
    [6] Cressie N, 1993. Statistics for Spatial Data. New York: WileyInterscience, 15: 105–209.
    [7] Das D K, Bandyopadhyay S, Chakraborty D et al., 2009. Application of modern techniques in characterization and management of soil and water resources. Journal of the Indian Society of Soil Science, 57(4): 445.
    [8] Eldeiry A A, Garcia L A, 2010. Comparison of ordinary kriging, regression kriging, and cokriging techniques to estimate soil salinity using landsat images. Journal of Irrigation and Drainage Engineering, 136(6): 355–364. doi: 10.1061/(ASCE) IR.1943-4774.0000208
    [9] Emamgholizadeh S, Bahman K, Bateni S M et al., 2016. Estimation of soil dispersivity using soft computing approaches. Neural Computing and Applications, 1–10. doi: 10.1007/s 00521-016-2320-x
    [10] Emamgholizadeh S, Bateni S M, Jeng D-S, 2013. Artificial intelligence-based estimation of flushing half-cone geometry. Engineering Applications of Artificial Intelligence, 26(10):2551–2558. doi:  10.1016/j.engappai.2013.05.014
    [11] Emamgholizadeh S, Parsaeian M, Baradaran M, 2015. Seed yield prediction of sesame using artificial neural network. European Journal of Agronomy, 68: 89–96. doi: 10.1016/j.eja.2015. 04.010
    [12] Eslami M A, Shahsavani S, Roshani G A et al., 2016. Mapping soil fertility of the peyvand cooperative lands by arcgis. In:Water and Soil. Shahrood University of Technology, 120.
    [13] Fotheringham A S, Brunsdon C, Charlton M, 2003. Geographically Weighted Regression: The Analysis of Spatially Varying Relationships. London: John Wiley & Sons.
    [14] George D, 2011. Spss for windows step by step: a simple study guide and reference, 17.0 update, 10/e. Pearson Education India.
    [15] Ghorbani H, Kashi H, Hafezi Moghadas N et al., 2015. Estimation of soil cation exchange capacity using multiple regression, artificial neural networks, and adaptive neuro-fuzzy inference system models in golestan province, iran. Communications in Soil Science and Plant Analysis, 46(6): 763–780. doi: 10.1080/ 00103624.2015.1006367
    [16] Goovaerts P, 1998. Ordinary cokriging revisited. Mathematical Geology, 30(1): 21–42. doi:  10.1023/A:1021757104135
    [17] Ivajnši? D, Kaligari? M, ?iberna I, 2014. Geographically weighted regression of the urban heat island of a small city. Applied Geography, 53: 341–353. doi: 10.1016/j.apgeog.2014. 07.001
    [18] Kashi H, Emamgholizadeh S, Ghorbani H, 2014. Estimation of soil infiltration and cation exchange capacity based on multiple regression, ANN (RBF, MLP), and ANFIS models. Communications in Soil Science and Plant Analysis, 45(9):1195–1213. doi:  10.1080/00103624.2013.874029
    [19] Klute A, Dirksen C, 1986. Hydraulic conductivity and diffusivity:laboratory methods. In: Klute A. Methods of Soil Analysis:Part 1—Physical and Mineralogical Methods. 2nd ed. Madison: American Society of Agronomy, 687–734.
    [20] Kumar S, Lal R, Liu D S, 2012. A geographically weighted regression kriging approach for mapping soil organic carbon stock. Geoderma, 189–190: 627–634. doi: 10.1016/j.geoderma. 2012.05.022
    [21] Li Y, Li C K, Tao J-J et al., 2011. Study on spatial distribution of soil heavy metals in huizhou city based on BP-ANN modeling and GIS. Procedia Environmental Sciences, 10: 1953–1960. doi:  10.1016/j.proenv.2011.09.306
    [22] Liu F, Zhang G L, Sun Y J et al., 2013. Mapping the three- dimensional distribution of soil organic matter across a subtropical hilly landscape. Soil Science Society of America Journal, 77(4): 1241–1253. doi:  10.2136/sssaj2012.0317
    [23] Malinova T, Guo Z X, 2004. Artificial neural network modelling of hydrogen storage properties of Mg-based alloys. Materials Science and Engineering: A, 365(1–2): 219–227. doi: 10.1016/ j.msea.2003.09.031
    [24] Malvi U R, 2011. Interaction of micronutrients with major nutrients with special reference to potassium. Karnataka Journal of Agricultural Sciences, 24(1): 106–109.
    [25] McCulloch W S, Pitts W, 1943. A logical calculus of the ideas immanent in nervous activity. The Bulletin of Mathematical Biophysics, 5(4): 115–133. doi:  10.1007/BF02478259
    [26] McKenzie N J, Ryan P J, 1999. Spatial prediction of soil properties using environmental correlation. Geoderma, 89(1–2):67–94. doi:  10.1016/S0016-7061(98)00137-2
    [27] Mishra U, Lal R, Liu D S et al., 2010. Predicting the spatial variation of the soil organic carbon pool at a regional scale. Soil Science Society of America Journal, 74(3): 906–914. doi: 10.2136/sssaj2009.0158
    [28] Murayama Y, 2012. Progress in Geospatial Analysis. Japan:Springer Science & Business Media.
    [29] Nath T N, 2014. Status of macronutrients (N, P and K) in some selected tea growing soils of sivasagar district of Assam, India. International Research Journal of Chemistry, 7.
    [30] Odeh I O A, McBratney A B, Chittleborough D J, 1995. Further results on prediction of soil properties from terrain attributes:Heterotopic cokriging and regression-kriging. Geoderma, 67(3–4): 215–226. doi:  10.1016/0016-7061(95)00007-B
    [31] Olsen S R, 1954. Estimation of Available Phosphorus in Soils by Extraction with Sodium Bicarbonate. Washington: United States Department of Agriculture.
    [32] Reeves D W, 1997. The role of soil organic matter in maintaining soil quality in continuous cropping systems. Soil and Tillage Research, 43(1–2): 131–167. doi: 10.1016/S0167-1987(97) 00038-X
    [33] Rincón-Ruiz A, Pascual U, Flantua S, 2013. Examining spatially varying relationships between coca crops and associated factors in colombia, using geographically weight regression. Applied Geography, 37: 23–33. doi: 10.1016/j.apgeog.2012. 10.009
    [34] Robinson T P, Metternicht G, 2006. Testing the performance of spatial interpolation techniques for mapping soil properties. Computers and Electronics in Agriculture, 50(2): 97–108. doi: 10.1016/j.compag.2005.07.003
    [35] Saikh H, Varadachari C, Ghosh K, 1998. Changes in carbon, nitrogen and phosphorus levels due to deforestation and cultivation: A case study in simlipal national park, india. Plant and Soil, 198(2): 137–145. doi:  10.1023/A:1004391615003
    [36] Singh K P, Basant A, Malik A et al., 2009. Artificial neural network modeling of the river water quality—a case study. Ecological Modelling, 220(6): 888–895. doi: 10.1016/j.ecolmodel. 2009.01.004
    [37] Snyder P J, Redmond M P, 1995. Understanding neural networks. Computer explorations. Volumes 1 and 2. M. Caudill and C. Butler. Cambridge: MIT Press, 1992. Brain and Cognition, 27(1): 128–133. doi:  10.1006/brcg.1995.1012
    [38] Pang S, Li T X, Wang Y D et al., 2009. Spatial interpolation and sample size optimization for soil copper (Cu) investigation in cropland soil at county scale using cokriging. Agricultural Sciences in China, 8(11): 1369–1377. doi:  10.1016/S1671-2927(08)60349-1
    [39] Sun W, Minasny B, McBratney A, 2012. Analysis and prediction of soil properties using local regression-kriging. Geoderma, 171–172: 16–23. doi:  10.1016/j.geoderma.2011.02.010
    [40] Wackernagel H, 2003. Multivariate Geostatistics: an Introduction with Applications. Berlin Heidelberg: Springer Verlag.
    [41] Walkley A, Black I A, 1934. An examination of the degtjareff method for determining soil organic matter, and a proposed modification of the chromic acid titration method. Soil Science, 37(1): 29–38. doi:  10.1097/00010694-193401000-00003
    [42] Wang K, Zhang C R, Li W D, 2013. Predictive mapping of soil total nitrogen at a regional scale: a comparison between geographically weighted regression and cokriging. Applied Geography, 42: 73–85. doi:  10.1016/j.apgeog.2013.04.002
    [43] Western A W, Zhou S-L, Grayson R B et al., 2004. Spatial correlation of soil moisture in small catchments and its relationship to dominant spatial hydrological processes. Journal of Hydrology, 286(1–4): 113–134. doi: 10.1016/j.jhydrol.2003.09. 014
    [44] Zhang C S, Tang Y, Xu X L et al., 2011. Towards spatial geochemical modelling: use of geographically weighted regression for mapping soil organic carbon contents in ireland. Applied Geochemistry, 26(7): 1239–1248. doi: 10.1016/j.apgeochem. 2011.04.014
  • [1] Hongqiang JIANG, Ye WEI, Lin MEI, Zhaobo WANG.  Multiscale Characteristics and Connection Mechanisms of Attraction Networks: A Trajectory Data Mining Approach Leveraging Geotagged Data . Chinese Geographical Science, 2024, (): 1-15. doi: 10.1007/s11769-024-1417-x
    [2] Tian HE, Fuyuan LIU, Ao WANG, Zhanbo FEI.  Estimating Monthly Surface Air Temperature Using MODIS LST Data and an Artificial Neural Network in the Loess Plateau, China . Chinese Geographical Science, 2023, 33(4): 751-763. doi: 10.1007/s11769-023-1370-0
    [3] WEI Zongcai, ZHEN Feng, MO Haitong, WEI Shuqing, PENG Danli, ZHANG Yuling.  Travel Behaviours of Sharing Bicycles in the Central Urban Area Based on Geographically Weighted Regression: The Case of Guangzhou, China . Chinese Geographical Science, 2021, 31(1): 54-69. doi: 10.1007/s11769-020-1159-3
    [4] LI Yungang, ZHANG Yueyuan, HE Daming, LUO Xian, JI Xuan.  Spatial Downscaling of the Tropical Rainfall Measuring Mission Pre-cipitation Using Geographically Weighted Regression Kriging over the Lancang River Basin, China . Chinese Geographical Science, 2019, 20(3): 446-462. doi: 10.1007/s11769-019-1033-3
    [5] GUO Long, ZHANG Haitao, CHEN Yiyun, QIAN Jing.  Combining Environmental Factors and Lab VNIR Spectral Data to Predict SOM by Geospatial Techniques . Chinese Geographical Science, 2019, 20(2): 258-269. doi: 10.1007/s11769-019-1020-8
    [6] LI Erling, YAO Fei, XI Jiaxin, GUO Chunyang.  Evolution Characteristics of Government-Industry-University-Research Cooperative Innovation Network for China's Agriculture and Influencing Factors: Illustrated According to Agricultural Patent Case . Chinese Geographical Science, 2018, 28(1): 137-152. doi: 10.1007/s11769-017-0924-4
    [7] YANG Jun, BAO Yajun, ZHANG Yuqing, LI Xueming, GE Quansheng.  Impact of Accessibility on Housing Prices in Dalian City of China Based on a Geographically Weighted Regression Model . Chinese Geographical Science, 2018, 28(3): 505-515. doi: 10.1007/s11769-018-0954-6
    [8] QIAO Weifeng, GAO Junbo, LIU Yansui, QIN Yueheng, LU Cheng, JI Qingqing.  Evaluation of Intensive Urban Land Use Based on an Artificial Neural Network Model:A Case Study of Nanjing City, China . Chinese Geographical Science, 2017, 27(5): 735-746. doi: 10.1007/s11769-017-0905-7
    [9] TANG Qian, LIANG Guofu, LU Xunling, DING Shengyan.  Effects of Corridor Networks on Plant Species Composition and Diversity in an Intensive Agriculture Landscape . Chinese Geographical Science, 2014, 0(1): 93-103. doi: 10.1007/s11769-014-0659-4
    [10] ZHANG Haitao, GUO Long, CHEN Jiaying, FU Peihong, GU Jianli, LIAO Guangyu.  Modeling of Spatial Distributions of Farmland Density and Its Temporal Change Using Geographically Weighted Regression Model . Chinese Geographical Science, 2014, 0(2): 191-204. doi: 10.1007/s11769-013-0631-8
    [11] MO Minghao, WANG Xuelei, WU Houjian, CAI Shuming, Xiaoyang ZHANG, WANG Huiliang.  Ecosystem Health Assessment of Honghu Lake Wetland of China Using Artificial Neural Network Approach . Chinese Geographical Science, 2009, 19(4): 349-356. doi: 10.1007/s11769-009-0349-9
    [12] CAO Yungang, YANG Xiuchun, ZHU Xiaohua.  Retrieval Snow Depth by Artificial Neural Network Methodology from Integrated AMSR-E and In-situ Data——A Case Study in Qinghai-Tibet Plateau . Chinese Geographical Science, 2008, 18(4): 356-360. doi: 10.1007/s11769-008-356-2
    [13] LIU Jiying, WEN Jiahong, WANG Yafeng, WANG Weili, Beata M CATHSO, Kenneth C JEZEK.  Development and Applications of Dome A-DEM in Antarctic Ice Sheet . Chinese Geographical Science, 2007, 17(2): 160-165. doi: 10.1007/s11769-007-0160-4
    [14] LUO Jinming, DENG Wei, ZHANG Xiaoping, YANG Fan, LI Xiujun.  Characteristics of Channeling Flow in Cultivated Horizon of Saline Rice Soil . Chinese Geographical Science, 2006, 16(4): 342-346.
    [15] SHI Chun, Philip JAMES, GUO Zhong-yang.  APPLICATION OF ARTIFICIAL NEURAL NETWORK IN COMPLEX SYSTEMS OF REGIONAL SUSTAINABLE DEVELOPMENT . Chinese Geographical Science, 2004, 14(1): 1-8.
    [16] XIE Gao-di, CHEN Shen-bin, QI Wen-hu, LU Yao, YANG Xing-wei, LIU Cheng-liang.  A MULTIDISCIPLINARY AND INTEGRATED STUDY OF RICE PRECISION FARMING . Chinese Geographical Science, 2003, 13(1): 9-14.
    [17] WANG Zhi-chun, LI Qu-sheng, LI Xiu-jun, SONG Chang-chun, ZHANG Guang-xin.  SUSTAINABLE AGRICULTURE DEVELOPMENT IN SALINE-ALKALI SOIL AREA OF SONGNEN PLAIN, NORTHEAST CHINA . Chinese Geographical Science, 2003, 13(2): 171-174.
    [18] WANG Xie-kang, HUANG Er, CUI Peng.  SIMULATION AND PREDICTION OF DEBRIS FLOW USING ARTIFICIAL NEURAL NETWORK . Chinese Geographical Science, 2003, 13(3): 262-266.
    [19] AN Kai, XIE Gao-di, LENG Yun-fa, XIAO Yu.  DESIGN OF FARMLAND GIS FOR PRECISION AGRICULTURE . Chinese Geographical Science, 2003, 13(1): 20-24.
    [20] WANG Yi-yong, YANG Yong-xing.  EFFECTS OF AGRICULTURE RECLAMATION ON THE HYDROLOGIC CHARACTERISTICS IN THE SAN JIANG PLAIN, CHINA . Chinese Geographical Science, 2001, 11(2): 163-167.
  • 加载中
计量
  • 文章访问数:  346
  • HTML全文浏览量:  19
  • PDF下载量:  490
  • 被引次数: 0
出版历程
  • 收稿日期:  2016-11-16
  • 修回日期:  2017-01-25
  • 刊出日期:  2017-10-27

Comparison of Artificial Neural Networks, Geographically Weighted Regression and Cokriging Methods for Predicting the Spatial Distribution of Soil Macronutrients (N, P, and K)

doi: 10.1007/s11769-017-0906-6
    基金项目:  Under the auspices of Shahrood University of Technology,Iran (No.348517)
    通讯作者: Samad EMAMGHOLIZADEH,E-mail:s_gholizadeh517@shahroodut.ac.ir

摘要: Soil macronutrients (i.e. nitrogen (N), phosphorus (P), and potassium (K)) are important soils components and knowing the spatial distribution of these parameters are necessary at precision agriculture. The purpose of this study was to evaluate the feasibility of different methods such as artificial neural networks (ANN) and two geostatistical methods (geographically weighted regression (GWR) and cokriging (CK)) to estimate N, P and K contents. For this purpose, soil samples were taken from topsoil (0-30 cm) at 106 points and analyzed for their chemical and physical parameters. These data were divided into calibration (n=84) and validation (n=22). Chemical and physical variables including clay, pH and organic carbon (OC) were used as auxiliary soil variables to estimate the N, P and K contents. Results showed that the ANN model (with coefficient of determination R2=0.922 and root mean square error RMSE=0.0079%) was more accurate compared to the CK model (with R2=0.612 and RMSE=0.0094%), and the GWR model (with R2=0.872 and RMSE=0.0089%) to estimate the N variable. The ANN model estimated the P with the RMSE of 3.630 ppm, which was respectively 28.93% and 20.00% less than the RMSE of 4.680 ppm and 4.357 ppm from the CK and GWR models. The estimated K by CK, GWR and ANN models have the RMSE of 76.794 ppm, 75.790 ppm and 52.484 ppm. Results indicated that the performance of the CK model for estimation of macro nutrients (N, P and K) was slightly lower than the GWR model. Also, the accuracy of the ANN model was higher than CK and GWR models, which proved to be more effective and reliable methods for estimating macro nutrients.

English Abstract

Samad EMAMGHOLIZADEH, Shahin SHAHSAVANI, Mohamad Amin ESLAMI. Comparison of Artificial Neural Networks, Geographically Weighted Regression and Cokriging Methods for Predicting the Spatial Distribution of Soil Macronutrients (N, P, and K)[J]. 中国地理科学, 2017, 27(5): 747-759. doi: 10.1007/s11769-017-0906-6
引用本文: Samad EMAMGHOLIZADEH, Shahin SHAHSAVANI, Mohamad Amin ESLAMI. Comparison of Artificial Neural Networks, Geographically Weighted Regression and Cokriging Methods for Predicting the Spatial Distribution of Soil Macronutrients (N, P, and K)[J]. 中国地理科学, 2017, 27(5): 747-759. doi: 10.1007/s11769-017-0906-6
Samad EMAMGHOLIZADEH, Shahin SHAHSAVANI, Mohamad Amin ESLAMI. Comparison of Artificial Neural Networks, Geographically Weighted Regression and Cokriging Methods for Predicting the Spatial Distribution of Soil Macronutrients (N, P, and K)[J]. Chinese Geographical Science, 2017, 27(5): 747-759. doi: 10.1007/s11769-017-0906-6
Citation: Samad EMAMGHOLIZADEH, Shahin SHAHSAVANI, Mohamad Amin ESLAMI. Comparison of Artificial Neural Networks, Geographically Weighted Regression and Cokriging Methods for Predicting the Spatial Distribution of Soil Macronutrients (N, P, and K)[J]. Chinese Geographical Science, 2017, 27(5): 747-759. doi: 10.1007/s11769-017-0906-6
参考文献 (44)

目录

    /

    返回文章
    返回